Generate synthetic GelSight tactile images and depth maps from 3D meshes using Blender.

This is the official codebase for the paper "Sensor-Invariant Tactile Representation" (ICLR 2025).

[ICCV 2025] GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping under Flexible Language Instructions

Official PyTorch implementation of ChAda-ViT [CVPR 2024]

Code for "Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens" (CVPR 2026).

Decoupling common and unique representations for multimodal self-supervised learning

Fast Robot Kinematics and Dynamics in JAX

The official repository of Qwen-VLA

A Minimalist, Batteries-included Repository for Advancing World Model Science.

Damiao Motor Control Library – A Python library for controlling Damiao motors via CAN. Supports Windows, Linux, and macOS. Flexible control modes and real-time motor status feedback. 达妙电机控制库 – 一个用于…

[CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

[CVPR 2026] RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation

A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.

[RSS 2026] TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance

[ICML 2026 Oral] Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[CVPR 2026] VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Official implementation of "RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics"

We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.

RoboClaw is an Embodied AI Assistant.

[NeurIPS 2025] Official implementation of "RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics"

Official code for "Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation" (ICLR2026)

Implementation of "RoboAgent: Chaining Basic Capabilities for Embodied Task Planning"

The official implementation of "DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation". (arXiv 2601.22153)

Visual-Auditory-Tactile Manipulation Data Collector for Imitation Learning